Unverified50% confidenceFactExact time
Latent Sparse Attention (LSA) is an efficient attention method whose core is to hierarchically cluster keys in a learned latent space, with queries scoring the cluster hierarchy rather than scoring each key individually.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedThe model introduces QSA, a self-developed absorptive Attention mechanism from Tongyi Qianwen, which is highly similar in concept to DeepSeek's DSA (DeepSeek Sparse Attention).71% similarUnverifiedDeepMind的Griffin将基于线性递归单元LRU的循环层与局部注意力层交替堆叠66% similarVerifiedDeepSeek V4 adopts a proprietary hierarchical compressed attention strategy, featuring two alternating attention modes: CSA (Compressed Sink Attention) and HCA (Heavy Compressed Attention).66% similarUnverifiedA learned selector is usually a lightweight network (such as a small MLP or low-rank projection) that takes the current query vector and the key vectors of candidate tokens, quickly scores them, and selects the Top-k most relevant tokens to participate in the actual attention computation.65% similarUnverifiedDeepSeek-V3.2-Exp首次引入自研的DeepSeek Sparse Attention（DSA）稀疏注意力技术64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1126136API
curl https://kongchang.com/api/v1/knowledge/claims/1126136MCP
get_claim(id=1126136)